Tool Use

Tool use is the capability that separates an AI agent from a plain chatbot: the model can call out to external tools rather than only generating text. Anthropic uses the term "tool use" for the same underlying primitive that OpenAI labels function calling. A tool is any capability exposed to the model with a name, a description, and an input schema, such as a web search, a calculator, a shell command, or a database query. The model reads the tool descriptions, decides which to invoke, and emits a structured request; the host application runs the tool and returns the output.

From single tools to toolchains

A model rarely uses a tool once. In an agentic loop it observes a result, reasons about it, and may call another tool, repeating until the task is done. The quality of a tool's description matters as much as its code, because the model selects tools purely from the natural-language and schema hints it is given. Vague descriptions cause wrong or missing calls.

Sovereignty angle

For a self-hosted operator, tool use is where a local model gains real reach over your infrastructure, and therefore where the security boundary lives. Tools should run with least privilege, validate their inputs, and ideally pass through a human-in-the-loop checkpoint for irreversible actions. Standard interfaces like the Model Context Protocol aim to make tools portable across models without surrendering control of where execution happens.

Tool use underpins the agentic workflow and gives agents the hands they need to affect the world beyond a text box. D-Central treats tool definitions as a first-class part of any sovereign AI deployment.